Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add haberlah/replit-prd-skill --skill replit-prd-skillgit clone --depth 1 https://github.com/haberlah/replit-prd-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/haberlah/replit-prd-skill/replit-prd-skill)<a href="https://agentmods.dev/skills/haberlah/replit-prd-skill/replit-prd-skill"><img src="https://agentmods.dev/badge/skills/haberlah/replit-prd-skill/replit-prd-skill.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00086 | $0.00764 |
| Opus 5 | $0.00043 | $0.00382 |
| Sonnet 5 | $0.00017 | $0.00153 |
| Haiku 4.5 | $0.00009 | $0.00076 |
Grade A, and why
replit-prd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Replit PRD Generator
Create sequential, dependency-ordered prompt sequences that guide Replit Agent through complex project development.
Workflow
1. Research (Mandatory)
Before writing any PRD, search for current Replit capabilities:
□ "Replit Agent [current year, current month] capabilities"
□ "Replit Database PostgreSQL [current year, current month]"
□ "Replit App Storage"
□ "[specific technology] Replit [current year, current month]"
See references/research.md for the complete checklist.
2. Clarify
Gather from user:
- Core functionality and features
- Deployment target (Autoscale vs Reserved VM)
- User expertise level
- Any existing code or constraints
3. Sequence
Map feature dependencies and determine phase order. Always establish foundations before dependent features:
- Database schema before queries
- Shared hooks/utilities before components using them
- Layout structure before features filling it
- API patterns before features calling them
4. Deliver
Prompt 0 (Plan Mode): Full project context. Ask Agent to confirm understanding before building.
Prompts 1-N (Build Mode): Sequential phases with:
- Clear objective
- Numbered requirements
- Technical details
- Integration notes
- Acceptance criteria (checkbox format)
- Checkpoint recommendation
See references/templates.md for exact prompt format.
5. Adapt
When user returns mid-project with screenshots or new requirements:
- Layout/data model changes → Restructure NOW
- Isolated new feature → Add as additional prompt
- Visual polish → Scoped prompt with DO NOT CHANGE section
See references/adaptation.md for patterns.
Replit Agent Modes
Plan Mode: Discuss architecture without modifying code. No charges. Use for Prompt 0.
Build Mode: Write and modify code. Creates checkpoints. Use for Prompts 1-N.
Key Principles
- Research before recommending — Always search current Replit capabilities, software libraries and packages
- Native over external — Replit Database and App Storage, not third-party
- Plan Mode first — Establish context before building
- Sequence by dependency — Foundations before features
- Testable phases — Each prompt ends with verifiable functionality
- Checkpoint discipline — Recommend saves after each phase
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 114 lines · 86 tokens per session scan A 385c42592f57
replit-prd is a skill published in the GitHub repository haberlah/replit-prd-skill (9 stars, last pushed 7mo ago), licensed MIT. It adds 86 tokens to every session and 764 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…